NHM Marsupial Skin Data Analysis
Jen Ball, Bruno Cassanova, Ellen Coombs, Emma Dunne, & Aislinn Pearson
19th May 2017
Fat-tailed Mouse Opossum Thylamys
Introduction
Meet Thylamys, the fat-tailed mouse opossum from South America!
Thylamys pallidor
We collected body measurements of 73 individuals from four species of Thylamys in NHM Mammal collection and analysed the results…
1. Which species is the cutest longest?
## Analysis of Variance Table
##
## Response: Total_length
## Df Sum Sq Mean Sq F value Pr(>F)
## Species 3 55763 18587.6 35.052 9.699e-14 ***
## Residuals 67 35529 530.3
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Call:
## lm(formula = Total_length ~ Species, data = marsupial)
##
## Residuals:
## Min 1Q Median 3Q Max
## -52.714 -11.739 2.235 15.500 53.714
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 238.000 5.757 41.341 < 2e-16 ***
## Specieskarimii -83.286 10.435 -7.981 2.6e-11 ***
## Speciespallidior -48.235 6.981 -6.909 2.2e-09 ***
## Speciesvenustus -2.714 8.427 -0.322 0.748
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 23.03 on 67 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.6108, Adjusted R-squared: 0.5934
## F-statistic: 35.05 on 3 and 67 DF, p-value: 9.699e-142. Does altitude affect size?
## Analysis of Variance Table
##
## Response: Altitude
## Df Sum Sq Mean Sq F value Pr(>F)
## Total_length 1 1355460 1355460 0.7971 0.3753
## Residuals 64 108827710 1700433##
## Call:
## lm(formula = Altitude ~ Total_length, data = marsupial)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1587.1 -995.6 -817.0 811.4 2689.7
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2521.018 918.878 2.744 0.00788 **
## Total_length -3.926 4.398 -0.893 0.37530
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1304 on 64 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.0123, Adjusted R-squared: -0.003131
## F-statistic: 0.7971 on 1 and 64 DF, p-value: 0.37533. Is there a relationship between the length of hind foot and body?
## Analysis of Variance Table
##
## Response: Hind_foot
## Df Sum Sq Mean Sq F value Pr(>F)
## Head_body 1 118.627 118.627 70.7803 6.775e-12 ***
## Species 3 50.922 16.974 10.1278 1.556e-05 ***
## Head_body:Species 3 8.642 2.881 1.7187 0.1722
## Residuals 63 105.588 1.676
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Call:
## lm(formula = Hind_foot ~ Head_body * Species, data = marsupial)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.4653 -0.6587 -0.0086 0.7369 5.0076
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.68237 2.44989 3.136 0.00260 **
## Head_body 0.06756 0.02066 3.271 0.00174 **
## Specieskarimii 0.53827 3.16268 0.170 0.86540
## Speciespallidior 0.23726 3.39545 0.070 0.94451
## Speciesvenustus 6.53074 3.17774 2.055 0.04402 *
## Head_body:Specieskarimii -0.03329 0.02995 -1.111 0.27061
## Head_body:Speciespallidior -0.01213 0.03303 -0.367 0.71459
## Head_body:Speciesvenustus -0.05891 0.02748 -2.144 0.03593 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.295 on 63 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.6279, Adjusted R-squared: 0.5866
## F-statistic: 15.19 on 7 and 63 DF, p-value: 1.872e-114. Do males and females differ in size?
Sample size = 37 males, 36 females.
Conclusions
We acknowlegde the significiant limiations of our research, but onwards and upwards to greater data sampling!
(Not a mouse opossum, but equally cute)